Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

10-2022

Abstract

Despite the demonstrated editing capacity in the latent space of a pretrained GAN model, inverting real-world images is stuck in a dilemma that the reconstruction cannot be faithful to the original input. The main reason for this is that the distributions between training and real-world data are misaligned, and because of that, it is unstable of GAN inversion for real image editing. In this paper, we propose a novel GAN prior based editing framework to tackle the out-of-domain inversion problem with a composition-decomposition paradigm. In particular, during the phase of composition, we introduce a differential activation module for detecting semantic changes from a global perspective, i.e., the relative gap between the features of edited and unedited images. With the aid of the generated Diff-CAM mask, a coarse reconstruction can intuitively be composited by the paired original and edited images. In this way, the attribute-irrelevant regions can be survived in almost whole, while the quality of such an intermediate result is still limited by an unavoidable ghosting effect. Consequently, in the decomposition phase, we further present a GAN prior based deghosting network for separating the final fine edited image from the coarse reconstruction. Extensive experiments exhibit superiorities over the state-of-the-art methods, in terms of qualitative and quantitative evaluations. The robustness and flexibility of our method is also validated on both scenarios of single attribute and multi-attribute manipulations. Code is available at https://github.com/HaoruiSong622/Editing-Out-of-Domain.

Keywords

Image reconstruction, Semantics

Discipline

Artificial Intelligence and Robotics

Research Areas

Software and Cyber-Physical Systems

Publication

Proceedings of 17th European Conference on Computer Vision, Tel Aviv, Israel, October 23-27, 2022

Volume

13677

First Page

1

Last Page

17

ISBN

9783031197895

Identifier

10.1007/978-3-031-19790-1_1

Publisher

Springer Nature

City or Country

Switzerland

Copyright Owner and License

Authors

Download

Share

COinS